An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Cognee to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn messy, unstructured data into a searchable web of facts.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through Cognee.

  1. 01

    Cognee add data

    This capability ingests raw text or documents into your Cognee datasets. It serves as the entry point for all your data before the graph is built.

  2. 02

    Cognee cognify

    This capability processes your ingested data to extract entities and build the actual knowledge graph structure. It handles the heavy lifting of identifying relationships and generating embeddings.

  3. 03

    Cognee search

    This capability lets you query your knowledge graph using natural language. It uses graph traversal and semantic search to return context-aware answers.

  4. 04

    Cognee get insights

    This capability retrieves structured entity relationships to reveal hidden connections across your knowledge base.

Real work

What teams actually run

01

Complex Research

Connect multiple research papers to find non-obvious links between different scientific discoveries.

02

Deep Document Analysis

Ingest legal or technical documents to map out the relationships between different clauses and entities.

03

Advanced Agent Reasoning

Give your AI agent a structured memory that allows it to follow logical chains of thought through a graph.

04

Knowledge Base Organization

Transform a pile of disorganized notes into a structured, searchable intelligence hub.

Automate a task

Put Cognee to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Cognee works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Cognee to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

920ms average. Fast in production.

Cognee is checked daily against the live service.

Daily averagePeak 1048ms
Oct 3Today
Fastest day
674ms
Slowest day
1048ms
14-day trend
Stable+4%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cognee, so you can see the experience inside your AI.

It does not authenticate your account with Cognee. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Cognee Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_c6i3hXOYfoGrkpkYTLcBWkNZG3FKUa2WjFOiOwHJ/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Cognee capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "cognee-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_c6i3hXOYfoGrkpkYTLcBWkNZG3FKUa2WjFOiOwHJ/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Cognee in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Cognee owners hand off.

This MCP is built for anyone needing to move beyond basic document retrieval toward deep reasoning.

  • 01

    AI Engineers

    Building advanced RAG pipelines that require relationship-aware reasoning.

  • 02

    Data Analysts

    Turning massive sets of unstructured documents into structured, queryable insights.

  • 03

    Knowledge Managers

    Organizing complex organizational information into a searchable, interconnected graph.

FAQ

Questions Cognee owners ask.

  • 01

    How is Cognee different from standard RAG?

    Standard RAG relies on vector similarity to find text snippets. Cognee builds a knowledge graph that understands the specific relationships between entities, allowing for much deeper reasoning.

  • 02

    What kind of data can I ingest?

    You can ingest raw text, documents, or structured data into named datasets for processing.

  • 03

    Do I need to host the Cognee infrastructure?

    No, Vinkius hosts and manages the MCP for you. You just connect your client and start using the capabilities.

  • 04

    Can my AI agent use this for reasoning?

    Yes, the graph-aware search and entity relationship capabilities are designed specifically to help your agent reason through connected facts.

  • 05

    What clients are compatible with this MCP?

    This MCP works with any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 06

    What search types are available?

    Cognee supports four retrieval strategies: GRAPH_COMPLETION (default. combines vector search + graph traversal + LLM reasoning for context-aware answers), SUMMARIES (fast hierarchical overview search), INSIGHTS (structured entity relationships), and CHUNKS (pure vector similarity for raw text passages). Each strategy optimizes for different use cases.

  • 07

    Is Cognee open-source?

    Yes! Cognee is fully open-source under the Apache 2.0 license. You can self-host the entire platform including the knowledge graph engine, vector database, and API server. A managed cloud version with API keys is also available for teams that prefer not to manage infrastructure.

Explore

More in AI Frontier

Suggestions

Connect Cognee to Claude, Cursor, ChatGPT & more